Fraud detection system in casino

Abstract

A novel system is provided that detects cheating in games at an amusement park, or misses or cheating when betting or settling chips. A fraud detection system for detecting fraud in a game in which chips are collected and redeemed according to the win / loss result comprises a camera (2) that photographs chips (9) contained in a chip tray (17) of a dealer (5), an image analysis device (12) that analyzes the image captured by the camera (2) to detect the amount of chips (9) contained in the chip tray (17), a card distribution device (13) that determines the win / loss result of the game, and a control device (14) that detects fraud by comparing the win / loss result of the game with the amount of chips (9) contained in the chip tray (17) before and after the collection and redemption of chips.

Description

Technology Field

[0001] The present invention relates to a system for detecting misconduct in a game at a casino, or misconduct or fraud when betting or settling chips. Background Technology

[0002] At amusement facilities such as casinos, various attempts are being made to prevent fraud. These facilities are equipped with surveillance cameras to monitor for cheating, and they prevent fraud by analyzing footage obtained from these cameras to determine game irregularities or fraud involving the recovery or redemption of chips that differ from the actual win-loss results.

[0003] Meanwhile, it is proposed to determine the value of chips by attaching wireless IC (RFID) tags to each chip to determine the number of chips or the total amount bet.

[0004] In the card game monitoring system described in Patent Document 1, whether a chip placed on an organic table has been recovered or redeemed according to the win / loss result is determined by image analysis of the chip's movement, and monitoring of fraud is performed. Prior art literature

[0005] International Publication No. 2015 / 107902 The problem to be solved

[0006] The present invention aims to provide a novel system for detecting misconduct in games at an amusement facility, or mistakes or misconduct when betting or settling chips. means of solving the problem

[0007] A fraud detection system according to one embodiment of the present invention is a fraud detection system in an organic field having a plurality of organic tables, comprising: a game recording device that records a game state performed on the organic table as an image by means of a camera; an image analysis device that performs image analysis of the recorded game state image; a win / loss result determination device that determines the win / loss result of each game on the organic table; and a control device that detects fraudulent acts performed on the organic table by using the image analysis result by the image analysis device and the win / loss result determined by the win / loss result determination device. The control device identifies the location, type, and quantity of chips bet by each player through the image analysis device, and identifies the total amount of chips in the dealer's chip tray of the organic table; adds or subtracts the increase / decrease amount of chips in the game calculated from the location, type, and quantity of chips bet by all players in the game and the win / loss result of the game obtained by the win / loss result determination device, from the total amount of chips in the chip tray before the liquidation of each game, and the total amount of chips that should be in the chip tray after liquidation at the end of the game, and the The actual total amount of chips in the chip tray at the end of the game, obtained through an image analysis device, is compared, and it is determined whether there is a difference between the total amount that should be there and the actual total amount.

[0008] In the above-described fraud detection system, the control device may determine the location, type, and quantity of chips bet by each player through the image analysis device, determine the actual total amount of chips in the chip tray when all winning chips bet by each player have been collected, compare the actual total amount of chips in the chip tray with the total amount of chips that should be there (calculated by adding the increase in the chip tray in the game from the location, type, and quantity of chips bet by the losing player to the total amount of chips in the chip tray before the liquidation of each game), and determine whether there is a difference between the total amount that should be there and the actual total amount.

[0009] In the above-described fraud detection system, the control device may compare the total amount of chips that should be in the chip tray, calculated by adding the increase in the chip tray in the game to the position, type, and quantity of chips bet by the losing player from the total amount of chips in the chip tray before the settlement of each game, with the actual total amount of chips in the chip tray, and determine that there is no difference between the total amount that should be and the actual total amount, and further compare the total amount that should be in the chip tray after settlement at the end of the game with the actual total amount of chips in the chip tray at the end of the game obtained through the image analysis device, and determine that there is a difference between the total amount that should be and the actual total amount, determine that there is a payment error and generate a payment error signal indicating a payment error.

[0010] In the above-described fraud detection system, the chip tray is provided with a recovery chip tray for recovering and temporarily storing chips bet by a losing player, and the image analysis device and the control device may compare the amount of chips that should be in the recovery chip tray, calculated from the position, type, and number of chips bet by the losing player, with the actual total amount of chips in the recovery chip tray, and determine whether there is a difference between the total amount that should be in the recovery chip tray and the actual total amount.

[0011] In the above-mentioned fraud detection system, obtaining the actual total amount of chips in the chip tray after liquidation at the end of the game through the image analysis device is,

[0012] 1) When the redemption of winning chips is completed,

[0013] 2) When the cards used in the above game are retrieved and discarded in the disposal area of ​​the above table,

[0014] 3) When a predetermined button attached to the above-mentioned win / loss result determination device is pressed,

[0015] 4) Any of the following is acceptable when the marker indicating victory or defeat is returned to its original state.

[0016] In the above-mentioned fraud detection system, when the control device determines that the actual total amount of chips identified in the dealer's chip tray of the organic table does not correspond to the amount of chips bet by all players and the increase or decrease in chips calculated from the win or loss result of the game, the game recording device may be configured to be able to analyze the record of the game in which the difference occurred by assigning an index or time point to the acquired image, or to specify and play a scene of chip recovery or a scene of payment.

[0017] In the above-mentioned fraud detection system, the image analysis device or control device may be structured in such a way that it is possible to obtain information on the type, number, and location of the bet chips even if a plurality of chips placed on an organic table are partially or entirely hidden by the blind spot of the camera.

[0018] In the above-mentioned fraud detection system, the control device is,

[0019] 1) Identify the location, type, and quantity of chips bet at each player position on the organic table, and compare each player's win-loss history and the amount of chips obtained from the win-loss results of each game with statistical data from past games to extract as unusual situations, or

[0020] 2) It is also acceptable to have a structure in which, at a play position on an organic table, the amount of betting chips when losing is smaller than the amount of betting chips when winning, which can be extracted as a unique situation by comparing it with statistical data of past games.

[0021] In the above-described fraud detection system, the control device may be capable of comparing and determining whether the amount of chips identified in the chip tray of the dealer of the organic table has increased or decreased in correspondence with the amount of chips corresponding to the exchanged banknotes or the amount of banknotes corresponding to the exchanged chips after the exchange of banknotes and chips is performed.

[0022] In the above-described fraud detection system, the control device may further be equipped with a database that records the history of the exchange of banknotes and chips, and may refer to the database at a set time or on a daily basis to determine whether the amount of chips identified in the chip tray of the dealer of the organic table has increased or decreased in correspondence with the payout amount of chips corresponding to the exchanged banknotes, or the total payout amount of banknotes corresponding to the exchanged chips.

[0023] In the above-described fraud detection system, the control device may be capable of identifying the player of the play location extracted as the difference or peculiar situation through the image analysis device.

[0024] In the above-described fraud detection system, the control device may have a warning function that notifies the presence of the specific player at another organic table when the specific player leaves their seat and sits at another organic table.

[0025] In the above-mentioned fraud detection system, the control device is,

[0026] 1) In each game, whether or not there is a movement of chips between the start of card drawing or between the dealer's game start operation and the display of the game's win / loss result by the card distribution device,

[0027] 2) After the end of each game, while the dealer is collecting the chips bet by the loser among the game participants, whether or not the said loser is taking the chips,

[0028] 3) After the end of each game, while the dealer is collecting the chips bet by the loser among the game participants, whether or not chips were added,

[0029] 4) After the end of each game, the dealer checks whether or not a payout has been made to the location of the chips bet by the winner among the game participants,

[0030] 5) After each game ends, the game may further be equipped with a function to determine whether or not the winner among the game participants has captured the chips bet and the chips paid out.

[0031] In the above-mentioned fraud detection system, the win / loss result determination device may be a card dispensing device that dispenses cards from a game table, or a control device that determines the win / loss result of each game from information from the image analysis device that reads the cards dispensed from the game table with a camera. Effects of the invention

[0032] According to the fraud detection system of the present invention, fraud in the recovery and redemption of chips based on the win or loss result of a game can be detected.

[0033] In addition, according to the system of the present invention, even if a card is bent due to a card squeegee by a player, which is frequently performed in games such as baccarat, the rank and suit of the card can be determined by image analysis, and the total amount of blind spots or overlapping chips can be identified along with their locations. Furthermore, fraud during the exchange of banknotes and chips can also be detected. Brief explanation of the drawing

[0034] FIG. 1 is a diagram showing an overall overview of an unauthorized detection system in an organic field having a plurality of organic tables according to a first embodiment of the present invention. FIG. 2a is a perspective view of a chip showing examples of different superposition states of the chip identified in each of the first embodiments of the present invention. FIG. 2b is a perspective view of a chip showing examples of different superposition states of the chip identified in each of the first embodiments of the present invention. FIG. 3a is a drawing showing details of a chip tray of a first embodiment of the present invention. FIG. 3b is a drawing showing another example of a chip tray of the first embodiment of the present invention. FIG. 4 is an enlarged view of a mark explaining the contamination of a card identified in the first embodiment of the present invention. FIG. 5a is a plan view showing the front of a marker of the first embodiment of the present invention. FIG. 5b is a plan view showing the back of the marker of the first embodiment of the present invention. FIG. 6 is a simplified explanatory diagram of the image of the exchange state between a banknote and a chip identified in the first embodiment of the present invention. FIG. 7 is a plan view showing the overall overview of a baccarat game fraud detection system of the second embodiment of the present invention. FIG. 8 is a plan view showing an overview of the progress state of a baccarat game in a fraud detection system of the second embodiment of the present invention. Figure 9 is an explanatory diagram showing the recovery of chips won by the casino side by the dealer in a baccarat game. FIG. 10 is an explanatory diagram showing the payment made by the dealer to the winning guest (game participant) in a baccarat game of the second embodiment of the present invention. FIG. 11 is an explanatory diagram showing the receipt of chips and payment by a winning guest (game participant) in a baccarat game of the second embodiment of the present invention. FIG. 12a is an explanatory diagram of an image that is subject to image analysis of the recovery of chips won by the casino side by the dealer in the second embodiment of the fraud detection system of the present invention. FIG. 12b is an explanatory diagram of an image that is subject to image analysis of the recovery of chips won by the casino side by the dealer in the fraud detection system of the second embodiment of the present invention. FIG. 12c is an explanatory diagram of an image that is subject to image analysis of the recovery of chips won by the casino side by the dealer in the fraud detection system of the second embodiment of the present invention. FIG. 13 is an explanatory diagram of an image that is the subject of image analysis of a chip's fraud detection system of the second embodiment of the present invention. FIG. 14a is an explanatory diagram of an image that is the subject of image analysis of the recovery of chips won by the game participant side in the second embodiment of the fraud detection system of the present invention. FIG. 14b is an explanatory diagram of an image that is the subject of image analysis of the recovery of chips won by the game participant side in the second embodiment of the fraud detection system of the present invention. FIG. 14c is an explanatory diagram of an image that is the subject of image analysis of the recovery of chips won by the game participant side in the second embodiment of the fraud detection system of the present invention. FIG. 14d is an explanatory diagram of an image that is the subject of image analysis of the recovery of chips won by the game participant side in the second embodiment of the fraud detection system of the present invention. FIG. 15 is a side cross-sectional view of a card distribution device in a second embodiment of the present invention. FIG. 16 is a drawing showing an example of a card of a second embodiment of the present invention. FIG. 17 is a plan view of the main part of the card guide portion of the card distribution device of the second embodiment of the present invention in a partially broken state. FIG. 18a is a side cross-sectional view of a main part showing a distribution restriction device that restricts the entry and exit of a card from a card storage part of a card distribution device of a second embodiment of the present invention. FIG. 18b is a side cross-sectional view of a main part showing a modified example of a distribution restriction device that restricts the entry and exit of a card from a card storage part of a card distribution device of a second embodiment of the present invention. FIG. 19 is a diagram showing the relationship between the output waveform of a sensor and a mark in a card distribution device of the second embodiment of the present invention. Specific details for implementing the invention

[0035] (First embodiment)

[0036] In amusement facilities such as casinos, chips are stacked high and placed on the amusement table. However, there is a problem in that the IC tag reader installed beneath the table cannot accurately read the total amount. Furthermore, if the sensitivity of the reader is increased, chips placed in different locations (where the outcome depends on the location) are added up, making it impossible to determine the total amount of chips for each location. Additionally, regarding imaging from a camera, there is a problem in that blind spots occur due to the camera's viewing angle, or the chips fall into shadows due to overlapping, making it impossible to determine the total amount of chips.

[0037] In addition, there is a problem in that the cards are bent due to card squeezing (an act of bending face-down cards to see the ranks of the cards little by little while playing the game) by the player, which is frequently done in baccarat games, and thus the ranks and suits of the cards cannot be determined through image analysis from the camera.

[0038] Furthermore, new challenges have been identified, as fraud in rigged tables has become more sophisticated. Specifically, fraud involving advanced betting methods—which cannot be detected by simple detections such as large winning amounts—cannot be found through cameras or the tracking of winning amounts. Additionally, conventional technology is insufficient to prevent fraudulent acts resulting from collusion between dealers and players.

[0039] In order to solve the above various problems, an unauthorized detection system in an organic field having a plurality of organic tables of the first embodiment is,

[0040] As a fault detection system in an organic field having multiple organic tables,

[0041] A game recording device that records the progress of a game performed on the above organic table as video through a camera, including a dealer and a player, and

[0042] An image analysis device for image analysis of the progress status of the game recorded above, and

[0043] A card dispensing device that determines and displays the win / loss results of each game in the above organic table, and

[0044] A control device is provided to detect fraudulent activity performed on the organic table by utilizing the image analysis result by the image analysis device and the win / loss result determined by the card distribution device.

[0045] In addition, as a fraud detection system, the card distribution device has a structure capable of reading the rank of the distributed card, and the control device has a structure capable of determining a match or mismatch by comparing the rank information obtained by the image analysis device from the image of each card distributed in the organic table with the rank information of the card read by the card distribution device.

[0046] In addition, as a fraud detection system, the image analysis device or control device is an artificial intelligence-based or deep learning structure capable of obtaining information on the rank of a card from a card that is distributed on an organic table and folded or contaminated by a player.

[0047] In addition, as a fraud detection system, the control device identifies the location, type, and quantity of chips bet by each player through the image analysis device, and determines whether the recovery of losing chips bet by each player and the payment of winning chips were properly carried out according to the win / loss result of the game by analyzing the video of the game's progress through the image analysis device.

[0048] In addition, as a fraud detection system, the image analysis device or control device is an artificial intelligence-based or deep learning structure capable of obtaining information on the type, number, and location of bet chips even if a plurality of chips placed on an organic table are partially or entirely hidden by the blind spot of the camera.

[0049] In addition, as a fraud detection system, the control device is an artificial intelligence-based or deep learning structure capable of comparing and calculating whether the amount of chips identified in the dealer's chip tray of the organic table has increased or decreased in correspondence with the recovery of the losing chips bet by each player and the payout amount of the winning chips after the game ends and is settled.

[0050] In addition, as a fraud detection system, the control device identifies the location and amount of chips bet at each player position of the organic table, and is an artificial intelligence-based or deep learning structure capable of extracting unique situations by comparing each player's win-loss history and the amount of chips obtained from the win-loss results of each game with statistical data of past games.

[0051] In addition, as a fraud detection system, the control device is an artificial intelligence-based or deep learning structure capable of extracting, by comparing with statistical data of past games, a state in which the amount of betting chips when losing at a certain organic table play position is smaller than the amount of betting chips when winning.

[0052] In addition, as a fraud detection system, the control device is structured to be capable of identifying individual players in a play position that has been extracted as an unusual situation through the image analysis device or has achieved a victory of more than a predetermined amount.

[0053] In addition, as a fraud detection system, the control device has a warning function that notifies the other organic table of the presence of the specific player when the specific player leaves their seat and sits at another organic table.

[0054] In order to solve the above various problems, the fault detection system in an organic field having a plurality of organic tables according to the present invention is,

[0055] A game recording device that records the progress of a game performed on the above organic table as video through a camera, including a dealer and a player, and

[0056] A card dispensing device that determines and displays the win / loss results of each game in the above organic table, and

[0057] An image analysis device for image analysis of the progress status of the game recorded above, and

[0058] A control device capable of detecting banknotes and chips in the organic table using the image analysis results of the image analysis device described above is provided,

[0059] The above image analysis device or control device is capable of detecting that an exchange of banknotes and chips is taking place on the organic table in a situation other than during card dealing, based on information obtained from the card distribution device or the dealer, and also recognizes the total amount of genuine banknotes verified by a black light, and also recognizes the total amount of chips even if a plurality of chips placed on the organic table as exchange targets are partially or entirely hidden by the blind spot of the camera, and is an artificial intelligence-utilizing or deep learning structure capable of comparing the total amount of banknotes from the player on the organic table with the total amount of chips from the dealer and determining whether the amounts of both match.

[0060] In addition, as a fraud detection system, the control device is an artificial intelligence-based or deep learning structure capable of comparing and calculating whether the amount of chips identified in the dealer's chip tray of the organic table has increased or decreased in correspondence with the amount of chips paid for the exchanged banknotes after the exchange of banknotes and chips has been performed and settled.

[0061] In addition, as a fraud detection system, the control device is an artificial intelligence-based or deep learning structure capable of comparing and calculating the consistency or discrepancy between the deposit amount of banknotes based on the dealer's input and the total amount of banknotes based on the image analysis result by the image analysis device after the exchange of banknotes and chips is performed and cleared. Furthermore, the control device is an artificial intelligence-based or deep learning structure capable of comparing and calculating the consistency or discrepancy between the total deposit amount of banknotes based on the dealer's input and the total amount of banknotes based on the image analysis result by the image analysis device at the organic table managed by the dealer.

[0062] According to the fraud detection system of the present embodiment, even if a card is bent due to a card squeeze by a player, which is frequently done in games such as baccarat, the rank and suit of the card can be determined by image analysis, and the total amount and location of dead or overlapping chips can also be identified. In addition, fraud during the exchange of banknotes and chips can also be detected.

[0063] The overall overview of the fraud detection system in an organic field having a plurality of organic tables according to the first embodiment of the present invention will be explained in more detail below. FIG. 1 is a diagram showing the overall overview of the system, and the fraud detection system in an organic field having a plurality of organic tables (4) comprises a game recording device (11) that records the progress state of a game performed on an organic table (4) as an image through a plurality of cameras (2), including a player (6) and a dealer (5), an image analysis device (12) that analyzes the image of the recorded progress state of the game, and a card distribution device (3) that determines and displays the win / loss result of each game on the organic table (4). The card distribution device (3) is a so-called electronic shoe that is already used by those skilled in the art, and has the rules of the game programmed in advance and is structured to read the information of the distributed card (C) and determine the win / loss of the game. For example, in a baccarat game, the Banker win, the Player win, and the Tie (draw) are basically determined by the rank of 2 to 3 cards, and the result of the judgment (win / loss result) is displayed on the result display lamp (13).

[0064] The fraud detection system also includes a control device (14) that compares the rank of the actual card based on the image analysis result by the image analysis device (12) with the win / loss result determined by the card distribution device (3) and detects fraud (such as discrepancy between the sum of the ranks of the distributed cards and the win / loss result) that occurs on the play table (4). The card distribution device (3) is structured to be able to read the rank (A, 2-10, J, Q, K) and suit (heart, spade, etc.) of the card (C) that is manually distributed by the dealer (5), and the control device (14) is structured to be able to determine whether there is a match or a discrepancy by comparing the rank and suit information obtained by the image analysis device (12) (using artificial intelligence) from the image of each card distributed on the play table (4) (taken using the camera (2)) with the card and suit information read by the card distribution device (3). The image analysis device (12) and control device (14) in the present fraud detection system are structured to have a complex combination of a computer, a program, and a memory, either as a single unit or in multiple units.

[0065] The image analysis device (12) and the control device (14) have an artificial intelligence-based or deep learning structure that can obtain information on the rank of the card even if the card (C) is distributed on the organic table (4) and is bent or contaminated by the player (6). As shown in FIG. 4, a situation arises where it is difficult to distinguish between clover and spade with the contaminated card (C). Even in such cases, the suit can be determined by image analysis and judgment using an artificial intelligence-based computer or control system and deep learning (structure) technology. Furthermore, even if the card is bent due to card squeezing by the player, which is frequently done in games such as baccarat, the suit or rank of the card before deformation can be recognized by using self-learning of multiple image deformation examples, an artificial intelligence-based computer or control system, and deep learning (structure) technology. Since the artificial intelligence-based computer or control system and deep learning (structure) technology are already available for use by those skilled in the art, a detailed description is omitted.

[0066] A control device (14) having an artificial intelligence-based or deep learning structure can determine, through a camera (2) and an image analysis device (12), where each player (6) has bet chips (9) in the betting area (8) (player, banker, or pair), the type of chips (9) bet (each chip (9) has a different amount value assigned to it for each color), and the number of chips (9). Chips (9) are stacked in an offset manner as shown in FIG. 2a, rather than stacked in a vertically aligned manner. In this case, if the camera (2) is positioned in the direction of the arrow X shown in FIG. 2a (or if the direction of the chips (9) is relatively obscured), it is assumed that the chips (9) are not visible (entered the obscured area) as shown in FIG. 2b. In the case of a computer or control system utilizing artificial intelligence or deep learning (structure) technology, self-learning functions, etc. are used to recognize hidden chips (9) due to blind spots (cases where part of a chip is hidden or the entire chip is hidden), and the number of chips is accurately determined. In this way, since it is possible to determine which location (player, banker, or pair) the chip (9) is bet on in the betting area (8), the type of chip (9) bet (the chip (9) is assigned a different amount value for each color), and the number of chips, the control device (14) determines whether the recovery of the losing chips (indicated by the arrow (L)) bet by each player (6) and the payment of the winning chips (9W) to the winning player (6W) were properly carried out according to the game's win / loss result determined by the card distribution device (3) in each game by analyzing the image of the game's progress state through the image analysis device (12).

[0067] The control device (14) can analyze and determine the total amount of chips (9) in the chip tray (17) of the dealer (5) of the organic table (4) using an image analysis device (12), and after the game ends and is settled, it can compare and calculate whether the total amount of chips (9) in the chip tray (17) has increased or decreased in correspondence with the amount of chips (9W) paid to the winning player (6W) with the winning chips bet by each player (6) after the game ends and is settled. Even though the total amount of chips (9) in the chip tray (17) is always known by means such as RFID, the control device (14) determines whether the amount of increase or decrease is correct by analyzing the image of the game's progress state through the image analysis device (12). These also utilize an artificial intelligence-based or deep learning structure.

[0068] In this example, fraud or miss is detected based on the result of the game's win or loss, information on how many chips of which type (9) were bet on which position (player, banker, or pair) in the betting area (8), and the amount of increase or decrease in chips (9) in the chip tray (17) after the recovery of the lost chips and the repayment of the winning chips (9) are completed. Therefore, fraud or miss can be detected without determining the movement of the chips (9) after the game ends, that is, whether the bet chips (9) moved to the player's side or to the dealer's side.

[0069] Here, the win / loss result of the game can be determined according to the rules of Baccarat by reading the rank of the card (C) sent out in the game from the card distribution device (3), for example, in the case of Baccarat. In addition, the win / loss result of the game can also be determined by photographing the organic table (4) with a camera (2), analyzing the image with an image analysis device (12), and comparing the analysis result with the rules of the game with a control device (14). In this case, the win / loss result determination device is composed of a camera (2), an image analysis device (12), and a control device (14). Information on how many chips (9) of which type are bet on which position (player, banker, or pair) in the betting area (8) by the player at each play position (7) is obtained by photographing the chips (9) placed in the betting area (8) with a camera (2) and analyzing the image for each play position (7) with an image analysis device (12).

[0070] Additionally, the increase or decrease in the amount of chips (9) in the chip tray (17) before and after the recovery of the winning chip (9) and the redemption of the winning chip (9) can be calculated by comparing the total amount of chips (9) in the chip tray (17) before the recovery of the winning chip (9) and the redemption of the winning chip (9) with the total amount of chips (9) in the chip tray (17) after the recovery of the winning chip (9) and the redemption of the winning chip (9). The total amount of chips (9) in the chip tray (17) before the recovery of the winning chip (9) and the redemption of the winning chip (9), and the total amount of chips (9) in the chip tray (17) after the recovery of the winning chip (9) and the redemption of the winning chip (9) can be detected by photographing the chip tray (17) containing the chips (9) with a camera (2) and analyzing the image with an image analysis device (12). In addition, by embedding an RFID indicating the amount within the chip (9) and providing an RFID reader in the chip tray (17), the total amount of the chips (9) contained in the chip tray (17) may be detected.

[0071] For example, the total amount of chips (9) in the chip tray (17) before the start of the game is Bb, and the total amount of chips (9) in the chip tray (17) after the game ends and the recovery of lost chips and the repayment of winning chips are completed is Ba. In addition, in this game, the total amount of chips (9) bet in the player area and all play positions (7) is bp, the total amount of chips (9) bet in the banker area and all play positions (7) is bb, and the total amount of chips (9) bet in the tie area and all play positions (7) is bt. For example, if the win / loss result of this game is a win for the banker, Ba-Bb = bp-bb+bt must hold. Alternatively, the total amount of chips (9) in the chip tray (17) after the end of the game, Ba, must be (Bb+bp-bb+bt). If this is not done, it may be determined that there was fraud or error in the recovery or redemption of the chip.

[0072] FIG. 3a is a drawing showing details of the chip tray of the present embodiment, and FIG. 3b is a drawing showing another example of the chip tray. The chip tray (17) is provided with a recovery chip tray (171) for recovering and temporarily storing chips (9L) bet by the losing player (6L) and a redemption chip tray (172) for storing chips (9W) to be redeemed. The image analysis device (12) and the control device (14) identify the location, type, and number of chips (9L) bet by the losing player (6L) and calculate the increase in chips (9L) in the game (the amount of chips (9) that should be in the recovery chip tray (171)). In addition, the image analysis device (12) and the control device (14) identify the actual total amount of chips (9) in the chip tray (171) after recovery and compare the total amount that should be with the actual total amount to determine whether there is a difference.

[0073] Additionally, the repayment of chips (9W) to the winning player (6W) is done by using the chips (9) in the repayment chip tray (172), thereby allowing sufficient time to determine the actual total amount of chips (9) in the repayment chip tray (171) after the image analysis device (12) and the control device (14) have recovered them.

[0074] The organic table (4) is provided with a disposal area (41) and / or a disposal slot (42) for disposing of cards (C) used in the game. Whenever the game ends, the cards (C) used in the game are collected and disposed of by placing them in the disposal area (41) or disposal slot (42) on the organic table (4).

[0075] The organic table (4) is further equipped with a marker (43) indicating the win or loss of the game. FIG. 5a is a plan view showing the front of the marker, and FIG. 5b is a plan view showing the back of the marker. In the baccarat game, two types of markers are used: a marker (43a) indicating the player's win and a marker (43b) indicating the banker's win. When the result of the game is announced, the dealer (5) flips over the marker of the winning side, either the player or the banker. This makes the win or loss of the game easily visible on the table. The flipped marker is returned to its original position by the dealer (5) after the chip (9) is collected and redeemed. Returning the marker to its original position also signifies that the next game can be started.

[0076] As described above, in this embodiment, the control device (14) calculates the balance of chips from the betting chip amount on the organic table (4) and the win / loss result of the game for each game, and verifies the increase in the balance of chips in the chip tray (17) after the game. If a difference is detected during this verification, the control device (14) notifies an alarm or adds a record to that effect to the video recording captured by the camera (2). The casino operator can investigate the cause of the difference by checking the video.

[0077] The fraud detection system of the present embodiment calculates the increase or decrease in chips in the game calculated from the position, type, and quantity of chips (9) bet by all players (6) in the game and the win / loss result of the game obtained from the win / loss result determination device, from the total amount of chips (9) in the chip tray (17) before the liquidation of each game, and compares the total amount of chips (9) that should be in the chip tray (17) after liquidation at the end of the game with the actual total amount of chips (9) in the chip tray (17) at the end of the game obtained through the image analysis device (12), and determines whether there is a difference between the total amount that should be and the actual total amount.

[0078] The control device (14) identifies the location, type, and quantity of chips bet by each player through the image analysis device (12), and when all the winning chips bet by each player are finished, determines the actual total amount of chips in the chip tray, compares the total amount of chips (9) in the chip tray (17) that should be there by adding the increase in the chip tray (17) in the game from the location, type, and quantity of chips bet by the losing player to the total amount of chips in the chip tray before the liquidation of each game, with the actual total amount of chips (9) in the chip tray (17), and determines whether there is a difference between the total amount that should be there and the actual total amount.

[0079] The control device (14) compares the total amount of chips (9) in the chip tray (17) that should be there, calculated by adding the increase in the chip tray (17) in the game from the position, type, and quantity of chips (9) bet by the losing player to the total amount of chips (9) in the chip tray (17) before the settlement of each game, with the actual total amount of chips (9) in the chip tray (17), and determines that there is no difference between the total amount that should be there and the actual total amount. Furthermore, it compares the total amount that should be there in the chip tray (17) after settlement at the end of the game with the actual total amount of chips (9) in the chip tray (17) obtained through the image analysis device (12), and if it determines that there is a difference between the total amount that should be there and the actual total amount, it determines that there is a payment error and generates a payment error signal indicating a payment error.

[0080] In the chip tray (17), a recovery chip tray (171) is provided for recovering and temporarily storing chips (9) bet by the losing player, and the image analysis device (12) compares the total amount of chips (9) in the recovery chip tray (171), calculated by adding the increase in chips (9) in the game calculated from the position, type, and number of chips (9L) bet by the losing player, with the actual total amount of chips (9) in the recovery chip tray (171), and determines whether there is a difference between the total amount that should be and the actual total amount.

[0081] When the control device (14) determines that the actual total amount of chips (9) identified in the chip tray (17) of the dealer (5) of the organic table (4) does not correspond to the amount of chips bet by all players and the amount of chips calculated from the win / loss result of the game, the game recording device (11) may assign an index or time to the acquired image, or specify and play back the scene of chip recovery or payment, so that the record of the game in which the difference occurred can be analyzed by the game recording device (11).

[0082] In this way, the control device (14) obtains the total amount of chips in the chip tray (17) after liquidation at the end of the game through the image analysis device (12), and the judgment after liquidation in this case is when any one of the following 1) to 4) occurs.

[0083] 1) When the redemption for the winning chip (9) is completed,

[0084] 2) When the card (C) used in the above game is recovered and disposed of in the disposal area (41) or disposal slot (42) of the above table,

[0085] 3) When a predetermined button attached to the win / loss result judgment device is pressed,

[0086] 4) When the marker (43) indicating victory or defeat is returned to its original state.

[0087] Additionally, the control device (14) is an AI-utilizing or deep learning structure capable of identifying the location (location where bets were placed on Player, Banker, or Pair) and amount (type and quantity) of chips bet at each play position (7) of the organic table (4), and comparing the win / loss history of each player (6) and the amount of chips obtained (winning amount) obtained by the win / loss result of each game with statistical data of a large number of past games (big data) to extract a unique situation (set by the casino). Typically, the control device (14) is equipped with an AI-utilizing or deep learning structure capable of extracting a unique situation by comparing it with statistical data of past games (big data, etc.), such as the occurrence of a winning amount of more than a certain amount (1 million dollars) or a state in which the amount of betting chips when losing and the amount of betting chips when winning continue for several games at a play position (7) of a certain organic table (4).

[0088] In addition, the control device (14) of the fraud detection system is structured to be able to identify individual players (6) in a play position (7) that has been extracted as an unusual situation (integrated with the image analysis device (12)) or has won more than a predetermined amount. The identification of such players (6) is achieved by obtaining an image of a face through feature point extraction, etc., in the image analysis device (12) and assigning an identity number (ID, etc.). Furthermore, the control device (14) has a warning function that notifies the other play table of the presence of the identified player (6) when the identified player leaves their seat and sits at another play table. Specifically, it notifies the pit manager or the person in charge of each play table (4) (which may also be a dealer) to further prevent unusual phenomena.

[0089] The control device (14) further includes a database that records the history of the exchange of banknotes (K) and chips (9), and at regular intervals or on a daily basis, refers to the database and determines whether the amount of chips (9) identified in the chip tray (17) of the dealer (5) of the organic table (4) has increased or decreased in relation to the amount of chips (9) paid for the exchanged banknotes (K), or the total amount of banknotes (K) paid for the exchanged chips (9).

[0090] In addition, in the above example, the win / loss history and the amount of chips obtained (winning amount) for each play position (7) may be monitored without specifying individual players (6). In this case, if each player (6) leaves their seat, the player (6) cannot be tracked, but unusual situations can be detected, such as when the amount of betting chips is small when losing and the amount of betting chips is large when winning at a specific play position (7) of one organic table (4), and this condition continues for several games. And, when such a play position (7) is detected, there is suspicion that there was fraud or a mistake at that play position (7). And, fraud or a mistake can be discovered by verifying the video of that play position (7).

[0091] Specifically, the camera (2) is installed to photograph chips (9) placed in the betting area (8) of at least the organic table (4). The image analysis device (12) analyzes the image captured by the camera (2) to detect which position of the player, banker, or tie chip is placed in the betting area (8) for each user position (7), and the amount of the placed chip. Additionally, the card distribution device (3) also functions as a win / loss result judgment device and determines the win / loss result of the game. The control device (14) records (monitors) the win / loss history and the amount of chips obtained (chip acquisition amount) for each play position (7) based on the position (player, banker, or body) within the betting area (8) where the chip (9) is placed and the win / loss result of the game. Additionally, only one of the win / loss history and chip acquisition amount may be recorded. The control device (14) identifies this player position (7) as a player position suspected of cheating when the win / loss history and / or chip acquisition history is in an unusual situation (set by the casino) compared with statistical data of a number of past games (big data).

[0092] When cheating is suspected at a certain player position (7), the cheat detection system may generate an alarm (light, sound, or vibration) at that time so that at least the dealer can perceive it. By doing so, the continuation of the cheating can be prevented, such as by stopping the game thereafter at that point. In addition, information indicating that cheating is suspected may be added to the video that is captured and recorded by the camera (2). By doing so, the cause of the suspected cheating can be identified by checking the video.

[0093] The fraud detection system in an amusement facility having an amusement table in this embodiment further includes a function to perform inspections during the exchange of banknotes and chips that are frequently performed on the amusement table (4). In an amusement facility such as a casino, before the game, the player (6) exchanges banknotes (cash, etc.) for amusement chips at a designated chip exchange station. However, if the player (6) runs out of chips, they can continue the game by exchanging cash (banknotes) for chips (9) on the amusement table (baccarat table, etc.) without leaving the amusement table (4). However, this creates an opportunity for fraud to occur between the dealer (5) and the player. The exchange of cash (banknotes) for chips (9) on the amusement table (baccarat table, etc.) needs to be performed when the game is not in progress. The card distribution device (3) is capable of detecting the start and end of card dealing (time of determining the win or loss) in order to determine the win or loss of the game. For this reason, the card distribution device (3) detects a situation other than card distribution (dealing), and the control device (14) detects that an exchange of banknotes and chips (9) is being performed on the organic table (4) in a situation other than card dealing (as shown in FIG. 6). Card dealing (or other situations) can be detected based on information obtained from the operation of the card distribution device (3) or the dealer (5).

[0094] The control device (14) can recognize the number of banknotes and the amount of banknotes by performing image analysis on the surface of the banknote (K). In addition, in the organic table (4), whether the banknote (K) to be exchanged with the chip (9) is genuine or not is determined by detecting the genuine mark (G) of the banknote by irradiating a black light. As shown in FIG. 6, the control device (14) verifies this genuine mark (G) by image analysis and recognizes the total amount of the genuine banknotes. Furthermore, even if multiple chips that are placed on the organic table as exchange targets are hidden by the blind spot of the camera (2), the total amount of the chips can be recognized. The control device is configured as an artificial intelligence-based or deep learning structure capable of comparing the total amount of banknotes (K) from the player on the organic table (4) with the total amount of chips (9) from the dealer (5) and determining whether the amounts of both match.

[0095] The control device (14) is an artificial intelligence-based or deep learning structure capable of comparing and calculating whether the total amount of chips (9) in the chip tray (17) of the dealer (5) of the organic table (4) has increased or decreased in correspondence with the amount of chips paid for the exchanged banknotes after the exchange of banknotes and chips has been performed and settled. It is also possible to consider cases where the total amount of chips (9) in the chip tray (17) of the dealer (5) is always known in advance by means of RFID of the chips (9). In addition, the total amount of chips (9) contained in the chip tray (17) can be detected by photographing the chip tray (17) containing the chips (9) with a camera (2) and analyzing the image with an image analysis device (12).

[0096] Additionally, the control device (14) verifies whether the increase or decrease in the amount of chips (9) in the chip tray (17) before and after the exchange of banknotes and chips matches the amount of chips exchanged as a result of image analysis on the organic table (4). The amount of banknotes paid may be entered into the control device (14) by the dealer (5) via key input, etc., or it may be determined by photographing the organic table (4) where the payment of banknotes is made using a camera (2) and analyzing the image with an image analysis device (12).

[0097] As described above, the control device (14) determines whether the amount of chips (9) reduced from the chip tray (17) due to the exchange of banknotes and chips matches the amount of banknotes paid from the player (6) to the dealer (5). Additionally, the control device (14) is an intelligent control device capable of comparing and calculating the match or mismatch between the amount of banknotes deposited by the dealer (5) (usually by key input, etc.) and the amount of banknotes calculated by the image analysis result of the image analysis device (12) after the exchange of banknotes and chips is performed and settled, and may also be an artificial intelligence-based or deep learning structure.

[0098] Furthermore, the control device (14) is an artificial intelligence-based or deep learning structure capable of comparing and calculating the agreement or disagreement between the total amount of banknotes based on the dealer's input in the organic table (4) managed by the dealer and the total amount of banknotes based on the image analysis result by the image analysis device (12).

[0099] The control device (14) determines whether the amount of chips (9) identified in the chip tray (17) of the dealer (5) of the organic table (4) has increased or decreased in correspondence with the amount of chips (9) corresponding to the exchanged banknotes or the amount of banknotes corresponding to the exchanged chips (9) after the exchange of banknotes and chips (9).

[0100] (Second embodiment)

[0101] Among the many table games played in amusement facilities such as casinos are Baccarat and Blackjack. These games use a standard deck consisting of 52 playing cards, and playing cards are distributed onto the amusement table from a card distribution device equipped with multiple decks (6 to 9 or 10 decks) that have been shuffled in advance, and the winner and loser are determined based on the number of distributed cards (rank) or game rules.

[0102] The distribution of cards from the card dispensing device and the settlement of bets to guests (game participants) are carried out by dealers or others in charge of the game table. In game venues such as casinos, efforts are being made to prevent errors or fraud in the settlement of these bets to guests (game participants).

[0103] In the card game monitoring system described in International Publication WO 2015 / 107902, a surveillance camera is used to read the movement of chips and check whether or not the bet amount is being paid to the winner.

[0104] In Baccarat or Blackjack, regarding bets by customers or the settlement of bet amounts by the dealer to customers (game participants), there is a problem in that the timing of these actions or who placed or took the chips cannot be detected, and therefore it is impossible to determine whether they are correct or not.

[0105] In order to solve the above various problems, the fault detection system of the second embodiment is a fault detection system in an organic field having a plurality of organic tables,

[0106] A game monitoring device that monitors the progress of a game played on an organic table using a camera, and

[0107] An image analysis device that performs image analysis on an image obtained from the above camera, and

[0108] A card dispensing device that determines and displays the win / loss results of each game in the above organic table, and

[0109] A control device is provided for determining the location of a chip placed by a game participant on the organic table using the analysis result of the image analysis device in each game, and for determining a winner and a loser among the participants of each game using the win / loss result.

[0110] The above control device is,

[0111] 1) In each game, whether or not there is a movement of chips between the start of card drawing or between the dealer's game start operation and the display of the game's win / loss result by the card distribution device,

[0112] 2) After the end of each game, while the dealer is collecting the chips bet by the loser among the game participants, whether or not there is any movement of chips by a person other than the dealer,

[0113] 3) After each game ends, while the dealer is collecting the chips bet by the loser among the game participants, whether chips were added,

[0114] 4) After the end of each game, the dealer checks whether or not a payout has been made to the location of the chips bet by the winner among the game participants,

[0115] 5) After each game ends, the system is equipped with a function to determine at least one of whether the winner among the game participants received the chips bet and the chips paid.

[0116] In addition, the control device may be configured to determine at least one of 1) to 5) by using the analysis result of the image analysis device to detect the movement of the dealer's and game participant's hands, the movement of the chips, or the movement of the hands and the chips.

[0117] In addition, the control device may be configured to determine whether the amount of chips paid to the winner by the dealer is correct based on the amount bet by the winner among the game participants.

[0118] In addition, the cheat detection system of the above game may further be equipped with a monitor or lamp that receives the judgment result and displays a warning or indication.

[0119] According to the fraud detection system of the present embodiment, regarding betting by a customer or settlement of betting amounts to a customer (game participant) by a dealer in Baccarat or Blackjack, it is possible to detect the timing of such actions and who placed or took the chips, and to detect these misses or fraudulent acts, issue a warning or display, and prevent recurrence.

[0120] Before proceeding with the detailed description of the present embodiment, the flow of a baccarat game performed in an amusement facility such as a casino will be explained. Additionally, in the second embodiment, components identical to those in the first embodiment will be described by assigning the same numbers.

[0121] As shown in FIG. 7, at the organic table (4), a guest (game participant / player) (6) sits in a playing position (chair) (7) facing the dealer (5). Then, the guest (game participant) (6) places a bet by placing chips (9) in the betting area (8) in front of them, indicating whether the Player or the Banker will win or a tie as the result of the Baccarat game (hereinafter referred to as "betting"). Then, the dealer (5) calculates the timing to end the betting by the guest (game participant) (6), calls "No More Bet" (ending betting), and performs actions such as moving the hand laterally (state shown in FIG. 7). In a baccarat game, after "No More Bet" is called and card withdrawal begins, or after the dealer (5) initiates the game, and before the game's win / loss result is displayed by the card distribution device (3), the guest (game participant) (6) cannot move chips, bet additional chips, or retrieve chips that were once bet.

[0122] After that, playing cards (1) are drawn one by one from the card distribution device (3) onto the playing table (4) with the back side facing upward. First, four cards are drawn, and as shown in 1 to 4 enclosed by circles in FIG. 8, the first card becomes the player's hand, the second card becomes the banker's hand, the third card becomes the player's hand, and the fourth card becomes the banker's hand, and are distributed and placed from the dealer (5) on the playing table (4) to the area (10) (player area (10P) and banker area (10B)) right in front. Then, based on the rank (number) of the 1st to 4th cards (1) and the conditions in the detailed rules of the baccarat game, the 5th card (1) and further, the 6th card (1) are drawn by the dealer (5), and these become the hand of the player or banker. Then, based on the rank (number) of the 1st to 4th cards (including the 5th and 6th cards in some cases) and the detailed rules of the baccarat game, the win or loss of the game is determined. Here, the card distribution device (3) has the rules of the game programmed in advance and is structured to read the information (rank (number) or suit) of the distributed cards (1) and determine the win or loss of the game. The win or loss determination result (win or loss result) determined by the card distribution device (3) is determined whether or not it matches the win or loss result determined by the dealer, etc. as described above.

[0123] Below, an overall overview of the fraud detection system for games in an amusement facility according to an embodiment of the present invention will be described. FIG. 7 is a diagram showing an overall overview of the system. The fraud detection system for games in an amusement facility comprises a game recording device (11) that records the progress of a game performed on an amusement table (4) as an image through a camera (2), including a guest (game participant) (6) and a dealer (5); an image analysis device (12) that analyzes the image of the recorded progress of the game; and a card distribution device (3) that has the function of determining and displaying the win / loss result of each game on the amusement table (4). The card distribution device (3) is a so-called electronic shoe that is already used by those skilled in the art, and has the rules of the game programmed in advance. It is structured to detect the timing at which a card (1) is distributed by the dealer (5) at the start of each game, and to read the information (rank (number) or suit) of each distributed card (1) to determine the win / loss of the game. For example, in a baccarat game, the Banker's win, the Player's win, and the tie are basically determined by the rank of 2 to 3 cards each, and the result of the judgment (win / loss result) is displayed on the indicator lamp (13).

[0124] The control device (14) of the fraud detection system is equipped with a chip detection function that determines whether a customer (6) (game participant) has placed a chip (9) on the player side or the banker side betting area (8) on the organic table (4) by using the analysis result of the image analysis device (12) for each game. The location and total amount of the chip (9) (whether the chip (9) has been placed on the player side or the banker side betting area (8)) are assumed to be in a state where they cannot be read normally, such as when the chip (9) is misaligned and overlapped, or when it is a blind spot from the position of the camera (2). The control device (14) is configured to accurately determine the location and number of chips by using a conventional AI-based computer or control system, a self-learning function based on deep learning technology, etc., to recognize the hidden state of the chip (9) due to a blind spot (when part of a chip is hidden, or when the entire chip is hidden). In addition, the structure for detecting the position and type of the chip (9) in the betting area (8) is not limited to this, and may be configured to detect, for example, by reading an ID embedded in the chip.

[0125] As described above, the control device (14) can identify the location (location where the player, banker, or pair is bet), type (each chip (9) is assigned a different amount value for each color), and quantity of chips (9) that each player (6) bets through the camera (2) and image analysis device (12), and can detect which customer (6) bet on the player (if there are multiple customers (6) bet on the player, which customer (6) bet the highest amount), and which customer (6) bet on the banker (if there are multiple customers (6) bet on the banker, which customer (6) bet the highest amount). The image analysis device (12) and the control device (14) in the fraud detection system are structured to have a complex combination of a computer, a program, and a memory, either as a single unit or as multiple components.

[0126] The control device (14) is structured to determine whether there is a match or a mismatch by comparing the rank and suit information obtained by the image analysis device (12) from the image (using camera (2)) of each card (1) distributed on the organic table (4) with the rank and suit information read by the card distribution device (3). In each game, the control device (14) determines whether the recovery of the winning chips (9) bet by the guest (game participant) (6) and the payment of the winning chips to the winning guest (game participant) (6) were properly carried out according to the game's winning or losing result determined by the card distribution device (3) by analyzing the image of the game's progress state through the image analysis device (12).

[0127] The control device (14), as a characteristic function of the present invention, determines whether or not a violation contrary to the rules is being committed by having the functions shown in 1) to 5) below according to the rules of the baccarat game. That is,

[0128] 1) In each game, between the signal that the card is drawn from the card dispensing device (3) or the game start operation by the dealer (5) pressing the start button (4s), and before the game win / loss result is displayed by the card dispensing device (3), whether or not there is movement of the chip (9) is monitored by the information obtained by the image analysis device (12) using the camera (2) (as shown in FIG. 8).

[0129] 2) After each game ends, while the dealer (5) is collecting the chips (9) bet by the loser among the game participants (6) (as shown in FIG. 9), whether the loser (6) is taking the chips (9) fraudulently is monitored by the information obtained by the image analysis device (12) using the camera (2).

[0130] 3) After each game ends, while the dealer (5) is collecting the chips (9) bet by the loser among the game participants, whether a person other than the dealer (5) (winner or loser) adds the winning chips (9W) or places new chips (9) on the winning side that did not bet is monitored by the information obtained by the image analysis device (12) using the camera (2).

[0131] 4) After each game ends, the dealer (5) monitors whether the winning player among the game participants (6) has correctly placed the payout chip (9W) at the location of the chip (9) they bet (as shown in FIG. 10) using the information obtained by the image analysis device (12) via the camera (2).

[0132] 5) After each game ends (the dealer (5) operates the card distribution device (3) to display the win / loss result on the display lamp (13)), the winner (6W) among the game participants (6) is monitored to see whether or not the bet chips (9) and paid chips (9W) have been taken (as shown in FIG. 11) by the information obtained by the image analysis device (12) using the camera (2).

[0133] The control device (14) performs the analysis of information obtained by the image analysis device (12) using the camera (2) as follows. That is, by using the analysis results of the image analysis device (12), monitoring of the above 1) to 5) is performed by detecting the movement of the hands of the dealer (5) and the game participant (6), the movement of the chips, or the movement of the hands and the chips. In the analysis that serves as the basis, it is at least necessary to know to whom the chips (9) have been taken. The method of analysis is explained below using FIGS. 12 to 14.

[0134] Analysis of chips (9) bet by the game participant (6L) and taken by the dealer (5) (Fig. 12).

[0135] The chips (9) bet by the game participant (6L) who lost the game are recovered by the dealer (5). Whether or not this has been recovered is monitored by analyzing the information obtained by the image analysis device (12) using the camera (2). First, the change from the state where the bet chips (9) exist (Fig. 12a) to the state where they do not exist (Fig. 12c) is detected by image analysis. Then, the image between the state where the chips (9) exist and the state where they do not exist (Fig. 12b) is analyzed. In the image between the state where the chips (9) exist and the state where they do not exist (Fig. 12b), the direction from which the hand (5h) is extended (whether it is from the upper direction in Fig. 12 or elsewhere) is analyzed. If it is extended from the upper direction (or the movement of the hand appearing from the upper direction and also exiting upward), the hand (5h) is determined to be the dealer's (5), and if the hand is extended from any other direction, it is determined to be fraud based on the rule that fraud is detected.

[0136] While the dealer (5) is collecting the chips (9) bet by the game participant (6L) who lost the game, it is monitored whether another person is fraudulently taking the chips (9) (Figs. 12 and 13). In the image between the state where the chips (9) exist and the state where they do not exist, as shown in Fig. 13, the analysis of what the loser (6L), etc., among the game participants (6) took is performed by detecting through image analysis that the hand (6h) is extending or moving from the lower part (originally from the upper part) of Fig. 13, and this is determined to be that a hand (6h), etc. other than the dealer (5), is taking the chips (9), and this is determined to be fraudulent.

[0137] Analysis of the winning chip (9) where the dealer (5) correctly pays out (places) the chip (9W), and the winner (6W) among the game participants (6) takes it.

[0138] First, regarding the winning chip shown in FIG. 14a, the chip (9W) is redeemed according to the rules of the game as shown in FIG. 14b. A change in the state shown in FIG. 14b is detected from the state shown in FIG. 14a, and at the same time, whether the hand is the dealer's (5) hand (5h) is detected by image analysis. Afterwards, as shown in FIG. 14c, the hand (6h) of the winner (6W) among the game participants (6) is extended (moved) to the same betting area, and then the control device (4) checks whether all the chips (9) are gone (state in FIG. 14d) according to the rules of the game from the image analysis result to determine whether there is any fraud.

[0139] Additionally, the control device (4) is configured to determine whether the amount of chips paid to the winner by the dealer (5) is correct based on the amount bet by the winner (6W) among the game participants (6). Specific examples are shown below. It is assumed that the position and total amount of the chips (9) (whether the chips (9) are bet in the betting area (8) on the player side or the banker side) cannot be read normally, such as when the chips (9) are misaligned and overlapped or when they are in a blind spot from the position of the camera (2). The control device (14) is configured to recognize the hidden state of the chips (9) due to blind spots (when part of a single chip is hidden, or when the entire chip is hidden) by utilizing existing AI-based computers or control systems, and self-learning functions based on deep learning (structure) technology, and to accurately determine the position and number of chips. In addition, the structure for detecting the position (8) and type of the chip (9) in the betting area (8) is not limited to this, and may be configured to detect, for example, by reading an ID embedded in the chip.

[0140] As described above, the control device (14) can identify the location (8) (location where the player, banker, or pair is bet), type (each chip (9) has a different amount of value assigned to it for each color), and quantity of chips (9) that each player (6) bets through the camera (2) and image analysis device (12), and can detect which customer (6) bet on the player (if there are multiple customers (6) bet on the player, which customer (6) bet the highest amount), and which customer (6) bet on the banker (if there are multiple customers (6) bet on the banker, which customer (6) bet the highest amount).

[0141] In addition, the control device (14) of the fraud detection system of the game monitors the information obtained by the image analysis device (12) using the camera (2) in the manner described above, in accordance with the rules of the baccarat game. It performs the monitoring shown in 1) to 5) described above and determines whether or not fraud has been committed in violation of the rules. When fraud is detected, the card distribution detection device (14C) lights up the abnormality indicator lamp (16) provided on both the card distribution device (3) and the organic table (4), and outputs the detection of fraud wirelessly or via wired connection (15) to the casino management department, etc. A monitor or lamp that receives the judgment result and displays a warning or indication may be additionally provided in another location.

[0142] As described above, fraudulent activity is detected by the control device (14), and at the time of detection or at an appropriate timing, in addition to sending a display signal to the indicator lamp (13) or the abnormality indicator lamp (16) of the card distribution device (3) or issuing a warning, the card distribution device (3) may activate a function to prevent card distribution after the time of detection of fraud or error, thereby preventing the distribution of the card (1).

[0143] Below, an embodiment of a card distribution device (3) used in the table game system of the present invention will be explained using FIGS. 15 to FIGS. 19. A card dispensing device (3) comprises a card receiving section (102) for receiving multiple shuffle playing cards (1s), a card guide section (105) for guiding shuffle playing cards (1) when a dealer (5), etc., manually draws shuffle playing cards (1) one by one from the card receiving section (102) toward the playing table (4), an opening section (106) for taking out the card (1) guided from the card guide section (105), a card detection section (card detection sensor (22 and 23)) for detecting that a shuffle playing card (1) has been drawn when a shuffle playing card (1) is drawn, a card reader section (108) for reading information indicating at least the number (rank) of shuffle playing cards (1), and the number (rank) of shuffle playing cards (1) read sequentially by the card reader section (108). Based on this, the device includes a control unit (109) that determines the win or loss of a card game, a result display lamp (13) that displays the win or loss result determined by the control unit (109), a distribution restriction device (30) provided in an opening (106) that restricts the entry and exit of a card (1) from the card storage unit (102), and a management control unit (114) that has the same function as the control unit (14), and these are integrated. When a dealer's mistake or misconduct in the game is detected by the control unit (14), the device has the function of preventing further card withdrawal from the card distribution device (3) after the point of detection or at a predetermined timing.

[0144] Next, a distribution restriction device (30) that restricts the entry and exit of a card (1) from a card storage unit (102) will be described using FIGS. 17 and FIGS. 18a. The distribution restriction device (30) is provided in the card guide (107) of the card guide unit (105) that guides the card (1) taken out one by one from the front opening (106) of the card storage unit (102) onto the organic table (4). The distribution restriction device (30) is provided with a structure in which, when the card (1) passes through the slot (33) between the card guide unit (105) and the guide cover of the card guide (107), a lock member (34) presses the card (1) to prevent the entry and exit of the card (1) within the slot (33). The lock member (34) moves as indicated by the arrow (m) so as to take two states: a position that presses the card (1) (limited position) and a passable position that allows the card (1) to pass through, by means of a driving unit (35), such as an electronic solenoid or a piezoelectric element. The driving unit (35) is controlled by a control unit (109) that is directly or indirectly connected to the control device (14) via wired or wireless connection, and moves the lock member (34) to two states: a position that presses the card (1) and a passable position that allows the card (1) to pass through. The rules of the baccarat game are pre-programmed and stored in the control unit (109).

[0145] Next, a modified example of the distribution limiting device (30) is described with reference to FIG. 18b. In the modified example, the distribution limiting device (40) is provided with a structure in which a lock member (36) protrudes into the slot (33) to prevent the movement of the card (1) when the card (1) passes through the slot (33) between the card guide part (105) and the card guide (107) (guide cover). The lock member (36) moves as indicated by the arrow (m) so as to take two states: a position that prevents the movement of the card (1) (limited position) and a passable position that allows the card (1) to pass through, driven by a driving part (37) such as an electronic solenoid or a piezoelectric element. The driving unit (37) is controlled by a control unit (109) connected to a control device (14) and moves the lock member (36) to two states: a position that prevents the movement of the card (1) and a position that allows the card (1) to pass through.

[0146] Next, details of the code reading unit (108) that reads a code (52) representing the number (number, rank) of the card (1) from the card (1) when the card (1) is manually withdrawn from the card receiving unit (102) will be described. FIG. 17 is a plan view of the main part of the card distribution device (3). In the drawing, the code reading unit (108) is provided in the card guide unit (105) that guides the card (1), which is manually withdrawn one by one from the front opening (106) of the card storage unit (102), onto the dispensing table (4). The card guide unit (105) is an inclined surface, and card guides (107) that also serve as sensor covers are attached to the edges on both sides. Additionally, each of the two card guides (107) is detachable using screws, etc. (not shown). When the card guides (107) are removed, the sensor group (115) of the code reading unit (108) is exposed. The sensor group (115) consists of four sensors and is composed of two ultraviolet reaction sensors (UV sensors) (20, 21) and object detection sensors (22, 23).

[0147] The object detection sensors (22, 23) are optical fiber type sensors that detect the presence or absence of the card (1) and can detect the movement of the card (1). The object detection sensor (22) is located on the upstream side of the card guide section (105) according to the flow direction of the card (1), and the other object detection sensor (23) is located on the downstream side. As shown in the drawing, both object detection sensors (22, 23) are provided on the upstream and downstream sides with UV sensors (20, 21) in between. The UV sensors (20, 21) are equipped with an LED (UV LED) that emits ultraviolet light and a detector. On the card (1), a mark (M) of the code (52) is printed using ultraviolet light-emitting ink that emits color when exposed to ultraviolet light, and ultraviolet light (black light) is irradiated onto the card (1), and the reflected light of the mark (M) of the code (52) on the card (1) is detected by the detector. UV sensors (20, 21) are connected to a code reading unit (108) and a control unit (109) via a cable. In the code reading unit (108), a combination of marks (M) is determined from the output signal of the detector of the UV sensors (20, 21), and a number (rank) corresponding to each code (52) is determined.

[0148] The code reading unit (108) controls the start and end of reading of the UV sensors (20, 21) by the control unit (109) based on the detection signal of the object detection sensors (22, 23). Additionally, the control unit (109) determines whether the card (1) has passed through the card guide unit (105) normally based on the detection signal of the object detection sensors (22, 23). As shown in FIG. 19, square marks (M) indicating the rank (number) and suit (heart or spade, etc.) of the card are arranged in 2 columns and 4 rows on the edge of the card (1). When the UV sensors (20, 21) detect the marks (M), they output an ON signal. The code reading unit (108) determines the relative relationship between the two signals input from the two UV sensors (20, 21). By this, the code reader (108) identifies the code based on the relative difference between two marks (M) detected by two UV sensors (20, 21), and identifies the number (rank) and type (suit) of the corresponding card (1).

[0149] FIG. 19 illustrates the relationship between the code (52) and the output of the ON signal of the two UV sensors (20, 21). Based on the result of comparing the relative change of the output of the ON signal of the UV sensors (20, 21), a predetermined combination of the mark (M) can be determined. Consequently, there are 4 types of combinations of the upper and lower two columns of the mark (M). If this is printed in 4 columns, 256 types of codes can be formed by raising 4 types to the power of 4. Each of the 52 types of playing cards is assigned to one of the 256 types of codes, and this is stored in memory or a program as a comparison table. The code reading unit (108) is configured such that by determining each code (52), the number (rank) and type (suit) of the card (1) are determined from a predetermined comparison table (not shown). In addition, since the 256 types of codes can be freely combined with the 52 types of cards and can be remembered by a comparison table, the combinations can be made complex and the combinations of the 256 types of codes and the 52 types of cards can be changed depending on the time or place. The codes are preferably printed with a paint that becomes visible when exposed to ultraviolet light and are printed in a position that does not overlap with the card type markings or index (103).

[0150] In addition, in the above embodiment, the image analysis device (12) or the control device (14) was a device having an artificial intelligence-based or deep learning structure, but the image analysis device (12) or the control device (14) may specifically perform image analysis or the above various controls using a Scale-Invariant Feature Transform (SIFT) algorithm, a Convolutional Neural Network (CNN), deep learning, machine learning, or the like. These technologies are technologies that perform image recognition on captured images and recognize objects included within the images, and in particular, recently, deep learning technology that multi-layers neural networks is used to recognize objects with high precision. This deep learning technology generally recognizes objects with high precision by overlapping layers in multiple stages in the intermediate layer between the input layer and the output layer of the neural network. In this deep learning technology, in particular, spiral neural networks are attracting attention for having higher performance than conventional image feature recognition.

[0151] In a spiral neural network, labeled target images are trained, and the main objects included in the target images are recognized. If multiple main objects exist within the training images, they are designated by rectangles, and training is performed by assigning labels to the images corresponding to the designated areas. Additionally, in the spiral neural network, it is also possible to determine the main objects within the images and their locations.

[0152] To further explain spiral neural networks, the object recognition process involves extracting candidate regions based on local features by performing edge extraction on the target image. These candidate regions are then input into the spiral neural network to extract feature vectors, followed by classification. The classified candidate region with the highest confidence level is obtained as the recognition result. Confidence level is a quantity that indicates how relatively high the similarity between a specific image region and a label learned with that subject is compared to the similarity of other classes.

[0153] In addition, devices having an artificial intelligence-based or deep learning structure are described in U.S. Patent No. 9361577, U.S. Patent Publication No. 2016-171336, U.S. Patent Publication No. 2015-036920, Japanese Patent Publication No. 2016-110232, etc., and these descriptions are incorporated into this specification by reference.

[0154] Although various embodiments of the present invention have been described above, the above-described embodiments are of course capable of being modified by those skilled in the art within the scope of the present invention, and the device of the present embodiment may be appropriately modified to meet the needs of the game to which it is applied.

[0155] In the present invention, the benefits of patent application number 2015-163213 filed in Japan on August 3, 2015, and patent application number 2015-206735 filed in Japan on October 1, 2015 are claimed, and the contents of said applications are incorporated herein by reference. Explanation of the symbols

[0156] 1: Playing card 1s: Shuffle Playing Cards of the Beast 2: Surveillance Camera 3: Card dispenser 4: Organic Table 5: Dealer 6: Guest (Game Participant / Player) 7: Play Location 8: Betting Area 9: Chip 10: Area 10P: Player Area 10B: Banker Area 11: Game recording device 12: Image analysis device 13: Result display lamp 14: Control unit 14C: Card distribution detection device 15: Output (abnormality judgment results, etc.) 16: Abnormal indicator lamp 30: Distribution restriction device 33: Slot 34: Lock missing 35: Drive unit 36: Lock missing 37: Drive unit 40: Distribution restriction device 102: Card slot 103: Index 105: Card Guide Section 106: Opening 107: Card Guide 109: Control unit 112: Side Monitor

Claims

Claim 1 A chip recognition system for recognizing a chip in an organic table in which a game is played using a chip having an RFID, comprising: an imaging means for generating at least one image or picture including at least a player playing a game on the organic table and a chip bet on the organic table by photographing the organic table; a judgment means for determining a person who has manipulated the chip by analyzing the image or picture generated by the imaging means, which includes the chip bet on the organic table and at least the hand of the player playing a game on the organic table, by means of an artificial intelligence-based or deep learning structure; and a first recognition means for recognizing an area on the organic table where the chip is placed and the type and number of the chip by reading the RFID of the chip bet on the organic table, wherein the organic table has a plurality of player positions, and each player position has a plurality of betting target areas arranged in the depth direction, and the judgment means determines a person who has taken the chip or a person who has placed the chip based on the image or picture when the presence or absence of the chip changes. Claim 2 A chip recognition system according to claim 1, further comprising a player-specific means for outputting at least one of an image or video including a player playing a game on the organic table, or information on the play position of a player playing a game on the organic table. Claim 3 In paragraph 2, the player-specification means is a chip recognition system that specifies a play location without specifying an individual player. Claim 4 In paragraph 2, the player identification means is a chip recognition system that identifies the ID of the player by analyzing an image or video including the face of a player playing a game on the organic table, generated by the imaging means, using an artificial intelligence-based or deep learning structure. Claim 5 A chip recognition system according to claim 1, wherein the imaging means comprises a first camera that generates an image or picture including at least the hand of a player playing a game on the organic table, and a second camera that generates an image or picture including at least a chip bet on the organic table. Claim 6 A chip recognition system according to claim 1, further comprising a control device for determining the total sum and / or history of chip betting amounts by a player at a predetermined point in time according to the progress of the game on the organic table. Claim 7 A chip recognition system according to claim 1, wherein the chips bet on the organic table are in an overlapping state, and further comprising a second recognition means for recognizing the type and number of chips in the overlapping state by analyzing an image or picture including the chips bet on the organic table generated by the imaging means using an artificial intelligence-based or deep learning structure. Claim 8 A chip recognition system according to claim 7, further comprising a game result determination means for determining the result of the game, and a control device for determining whether a chip in an overlapping state is a winning chip or a losing chip based on the result of the game determined by the game result determination means and the position of a plurality of chips in an overlapping state recognized by the second recognition means. Claim 9 In claim 8, the control device is also a chip recognition system that determines whether the above-mentioned chip has been accurately recovered based on the determination of the above-mentioned determination means. Claim 10 In claim 8, the control device is also a chip recognition system that determines whether payment has been made correctly for the winning chip based on the determination of the determination means.

Images